Power operation risk identification method and device based on dynamic downscaling technology

Abstract

The present invention relates to the technical field of meteorological risk identification, and discloses a method and device for identifying risks of electric power operations based on dynamic downscaling technology, the method comprising: acquiring multi-source data; fusing the multi-source data to generate a numerical forecast model analysis field; determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field; extracting meteorological risk elements of electric power operations based on the three-dimensional grid setting scheme; and generating corresponding risk identification results based on the meteorological risk elements of electric power operations. By fusing multi-source meteorological data, the accuracy of data analysis is improved, and the three-dimensional grid is further accurately determined, thereby achieving a downscaling effect and improving the accuracy of subsequent risk identification.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological risk identification, and in particular to a method for identifying risks of electric power operations based on dynamic downscaling technology and a device for identifying risks of electric power operations based on dynamic downscaling technology. Background Art

[0002] Power operations provide strong support and guarantee for the safe and stable operation of the power grid, and protect the safety of energy supply at the frontline. Power operations are mostly outdoor operations, involving multiple scenarios such as high-altitude operations, live operations, and near-electricity operations, and are greatly affected by potential meteorological risks. Therefore, quickly identifying the meteorological risks faced in power operations is of great significance to ensuring the personal safety of operators and the smooth implementation of power operations.

[0003] Due to the particularity of power operations, the identification of meteorological risks in power operations has very high requirements for the accuracy and spatiotemporal resolution of weather forecasts. At present, due to the influence of factors such as the systematic error of the forecast model itself, the error of observation data, and the resolution of the model, as well as the complex and changeable physical processes caused by the nonlinear motion of the atmosphere, the forecast accuracy of meteorological risk factors such as strong winds, heavy rains, high temperatures, and high humidity needs to be improved. There is still a big gap with the high spatiotemporal resolution requirements of meteorological risk identification in power operations, and it cannot meet the technical support for precise meteorological support for power operations. Summary of the invention

[0004] In order to overcome the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a method and device for identifying risks of power operations based on dynamic downscaling technology, which improves the accuracy of data analysis by fusing multi-source meteorological data and further accurately determines the three-dimensional grid, thereby achieving a downscaling effect and improving the accuracy of subsequent risk identification.

[0005] In order to achieve the above-mentioned objectives, an embodiment of the present invention provides a method for identifying risks of power operations based on dynamic downscaling technology, the method comprising: acquiring multi-source data; fusing the multi-source data to generate a numerical forecast model analysis field; determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field; extracting meteorological risk factors for power operations based on the three-dimensional grid setting scheme; and generating corresponding risk identification results based on the meteorological risk factors for power operations.

[0006] Preferably, the fusion processing of the multi-source data to generate a numerical forecast model analysis field includes: performing observation error analysis on the multi-source data based on preset covariance calculation rules to generate observation error covariance characteristics; generating an objective function based on the observation error covariance characteristics, minimizing the objective function to generate an optimal analysis field; performing operator analysis on the optimal analysis field based on analysis increments to generate a corresponding variational fusion observation operator; constructing a variational fusion model based on the multi-source data and the variational fusion observation operator; and performing data fusion operations based on the variational fusion model to generate a numerical forecast model analysis field.

[0007] Preferably, the observation error analysis of the multi-source data to generate observation error covariance characteristics includes: determining balance information of different variables in the multi-source data; calculating the standard deviation of different variables in the multi-source data; determining the self-adjoint smoothing factors of different variables in the multi-source data in different geographical directions; processing the balance information, the standard deviation and the self-adjoint smoothing factor based on a control variable conversion algorithm to generate observation error covariance characteristics for the multi-source data.

[0008] Preferably, the determining of the three-dimensional grid setting scheme based on the numerical forecast model analysis field comprises: determining the physical parameters to be analyzed based on the numerical forecast model analysis field; determining the climate characteristics and disaster characteristics within the power operation area; obtaining an initial-scale numerical forecast system; processing the initial-scale numerical forecast system based on the physical parameters to be analyzed, the climate characteristics and the disaster characteristics to generate a three-dimensional grid setting scheme.

[0009] Preferably, the determining of the physical parameters to be analyzed includes: performing physical parameter matching on the numerical forecast model analysis field to generate initial parameters; performing sensitivity analysis on the initial parameters to generate the most sensitive parameter combination; optimizing the most sensitive parameter combination based on preset optimization features to generate the physical parameters to be analyzed.

[0010] Correspondingly, the present invention also provides a device for identifying risks of power operations based on dynamic downscaling technology, the device comprising: a data acquisition unit for acquiring multi-source data; a fusion unit for fusing the multi-source data to generate a numerical forecast model analysis field; a grid setting unit for determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field; an extraction unit for extracting meteorological risk elements of power operations based on the three-dimensional grid setting scheme; and an identification unit for generating corresponding risk identification results based on the meteorological risk elements of power operations.

[0011] Preferably, the fusion unit includes: an analysis module, which is used to perform observation error analysis on the multi-source data based on preset covariance calculation rules to generate observation error covariance characteristics; a field generation module, which is used to generate an objective function based on the observation error covariance characteristics, and minimize the objective function to generate an optimal analysis field; an operator analysis module, which is used to perform operator analysis on the optimal analysis field based on analysis increments to generate a corresponding variational fusion observation operator; a model construction module, which is used to construct a variational fusion model based on the multi-source data and the variational fusion observation operator; a fusion module, which is used to perform data fusion operations based on the variational fusion model to generate a numerical forecast model analysis field.

[0012] Preferably, the analysis module is specifically used to: determine the balance information of different variables in the multi-source data; calculate the standard deviation of different variables in the multi-source data; determine the self-adjoint smoothing factors of different variables in the multi-source data in different geographical directions; process the balance information, the standard deviation and the self-adjoint smoothing factor based on the control variable conversion algorithm to generate observation error covariance characteristics for the multi-source data.

[0013] Preferably, the grid setting unit includes: a parameter determination module, used to determine the physical parameters to be analyzed based on the numerical prediction model analysis field; a feature determination module, used to determine the climate characteristics and disaster characteristics in the power operation area; a system acquisition module, used to acquire an initial-scale numerical prediction system; a scheme determination module, used to process the initial-scale numerical prediction system based on the physical parameters to be analyzed, the climate characteristics and the disaster characteristics, and generate a three-dimensional grid setting scheme.

[0014] Preferably, the parameter determination module is specifically used to: perform physical parameter matching on the numerical forecast model analysis field to generate initial parameters; perform sensitivity analysis on the initial parameters to generate the most sensitive parameter combination; optimize the most sensitive parameter combination based on preset optimization features to generate physical parameters to be analyzed.

[0015] Through the technical solution provided by the present invention, the present invention has at least the following technical effects:

[0016] By acquiring meteorological data of power operation scenarios from multiple data sources and fusing them, the comprehensiveness of the data is improved, and the data support for subsequent risk identification is enhanced; on this basis, the optimal three-dimensional grid setting scheme is further determined through the numerical forecast model analysis field, thereby achieving a downscaling effect, further improving the accuracy of meteorological risk identification for power operation scenarios, and meeting the actual needs of enterprises.

[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0019] Figure 1 It is a specific implementation flow chart of the power operation risk identification method based on the power downscaling technology provided by an embodiment of the present invention;

[0020] Figure 2 is a specific implementation flow chart of the fusion processing of the multi-source data provided by an embodiment of the present invention;

[0021] Figure 3 is a specific implementation flow chart of a three-dimensional grid setting scheme provided by an embodiment of the present invention;

[0022] Figure 4 It is a structural schematic diagram of a power operation risk identification device based on power downscaling technology provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0024] The terms "system" and "network" in the embodiments of the present invention can be used interchangeably. "Multiple" means two or more than two. In view of this, "multiple" can also be understood as "at least two" in the embodiments of the present invention. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the previous and subsequent associated objects are in an "or" relationship. In addition, it should be understood that in the description of the embodiments of the present invention, the words "first", "second", etc. are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0025] See also Figure 1 The embodiment of the present invention provides a method for identifying risks of power operations based on power downscaling technology, the method comprising:

[0026] S10) acquiring multi-source data;

[0027] S20) fusing the multi-source data to generate a numerical forecast model analysis field;

[0028] S30) constructing a three-dimensional space grid based on the numerical forecast model analysis field;

[0029] S40) extracting meteorological risk factors for power operations based on the three-dimensional spatial grid;

[0030] S50) Generate corresponding risk identification results based on the meteorological risk factors of the power operation.

[0031] In a possible implementation, multi-source data is first obtained. In this embodiment, the multi-source data includes but is not limited to ground meteorological observation data in the power operation area, high-altitude detection data, power grid micro-meteorological observation data, radar detection data and other multi-source meteorological observation data. It is easy for those skilled in the art to know that there may be problems with the initially obtained data, so in order to ensure the accuracy in the subsequent data analysis process, it is necessary to perform quality control on it.

[0032] In this embodiment, first, the multi-source data is checked for integrity. If the data integrity check is qualified, a data integrity check qualified mark is set, and the boundary value check operation is entered; if the data integrity check is unqualified, a quality check unqualified mark is set, and the unqualified data can be moved to the unqualified product table. Then, the data that has passed the integrity check is checked for boundary values. If the data boundary value check is qualified, a data boundary value check qualified mark is set, and the change range check operation is entered; if the data boundary value check is unqualified, a quality check unqualified mark is set, and the data is moved to the unqualified product table at the same time. Then, the data that has passed the boundary value check is checked for change ranges. If the data change range check is qualified, a data change range check qualified mark is set, and the spatial consistency check operation is entered; if the data change range check is unqualified, a quality check unqualified mark is set, and the data is moved to the unqualified product table at the same time. Further, the data that has passed the change range check is checked for spatial consistency. If the data space consistency check is qualified, a data space consistency check qualified mark is set, and the time consistency check operation is entered; if the data space consistency check is unqualified, a quality check unqualified mark is set, and the data is moved to the unqualified product table at the same time. Finally, a time consistency check is performed on the data that has passed the spatial consistency check. If the data time consistency check passes, the data time consistency check pass mark is set and the data quality identification operation is entered; if the data time consistency check fails, the quality check fail mark is set and the data is moved to the unqualified product table.

[0033] Finally, after the initial multi-source data has been checked as above, it is further corrected and reviewed by manual review and correction to finally generate data of qualified quality. On this basis, subsequent data fusion processing is carried out.

[0034] See also Figure 2In an embodiment of the present invention, the step of fusing the multi-source data to generate fused data includes:

[0035] S21) performing observation error analysis on the multi-source data based on a preset covariance calculation rule to generate observation error covariance features;

[0036] S22) generating an objective function based on the observation error covariance characteristics, performing minimization processing on the objective function, and generating an optimal analysis field;

[0037] S23) performing operator analysis on the optimal analysis field based on the analysis increment to generate a corresponding variational fusion observation operator;

[0038] S24) constructing a variational fusion model based on the multi-source data and the variational fusion observation operator;

[0039] S25) performing data fusion operations based on the variational fusion model to generate a numerical forecast model analysis field.

[0040] In a possible implementation, since the background field error covariance (B matrix) plays a vital role in determining the quality of variational fusion of numerical forecast models, it controls the percentage of observation information that becomes analysis increments, how each observation affects a wide area, and the balance between different analysis variables. Therefore, in an embodiment of the present invention, the B matrix is ​​implicitly included in the control variable conversion operator through the control variable conversion method to analyze the background error covariance characteristics of a specific area.

[0041] In an embodiment of the present invention, the observation error analysis of the multi-source data to generate observation error covariance characteristics includes: determining balance information of different variables in the multi-source data; calculating the standard deviation of different variables in the multi-source data; determining the self-adjoint smoothing factors of different variables in the multi-source data in different geographical directions; processing the balance information, the standard deviation and the self-adjoint smoothing factor based on a control variable conversion algorithm to generate observation error covariance characteristics for the multi-source data.

[0042] Specifically, first determine the balance information of different variables in the multi-source data, for example, analyze the different variables in the multi-source data and generate a matrix B representing the balance between the different variables. balance ; Then calculate the standard deviation of different variables in the multi-source data, for example, its standard deviation is represented by matrix V; and further determine the self-adjoint smoothing factors of different variables in the multi-source data in the east-west and north-south directions, for example, its self-adjoint smoothing factors are represented by matrix B x B y B y B xCharacterization, at this time, the above parameters are processed according to the control variable conversion algorithm to generate the corresponding observation error covariance characteristics, which are characterized as follows:

[0043]

[0044] in, The matrix is ​​the companion form of the equilibrium equation, B z The matrix represents the vertical smoothing factors for different variables.

[0045] In an embodiment of the present invention, the most important and complex background error covariance in the fusion analysis is decomposed into three sets of information through a control variable conversion algorithm: the balance is represented by a pre-calculated "regression coefficient" to represent the balance between different analysis variables; the standard deviation is represented by the square root of the pre-calculated analysis control variable variance to represent the quality of the background field, and the ratio of the background error variance to the observation error variance determines the degree of fit of the analysis field to the observation field; the horizontal and vertical influences are modeled as a Gaussian distribution with a pre-calculated "characteristic scale" parameter in the recursive filter, for example, the horizontal influence is modeled as a combination of three recursive filters with different influence scales, which determine the area and depth of the propagation of the observation information.

[0046] On this basis, according to the covariance characteristic analysis of the observation error of multi-source data in the power operation area, the observation operator is established to achieve effective deep fusion. In the specific implementation process, the objective function of the observation element x0 is first established, and then the objective function is minimized to obtain the optimal analysis field. In the embodiment of the present invention, the optimal analysis field is characterized as:

[0047]

[0048] Among them, x0 represents the initial state of the nonlinear forecast model, Represented as the observation data in the i-th time slot, H i Characterized as Observation The corresponding observation operator. The operator represents the integration of the nonlinear positive mode from the initial time t0 to t i moment, so is obtained by integrating the model i The mode state at the moment. i The moment mode state is from the previous moment t i―1 Integrating forward to the current moment, the general forecast problem can be expressed as: The meaning is to convert t i The mode state at a certain moment is mapped to a value in the observation space, and the superscripts T and -1 represent the transpose and inverse of the matrix, respectively.

[0049] At this time, the optimal analysis field is further analyzed by operators based on the analysis increment to generate the corresponding variational fusion observation operator. Specifically, the analysis increment is regarded as a disturbance of the initial state of the mode, and the background field is used as the starting value of the iteration, that is, The analysis of n iterations is obtained by adding the incremental update of the previous analysis to this step, that is: Bringing it into the optimal analysis field yields:

[0050]

[0051] The forecast model in the above formula exist Using Taylor expansion, we get:

[0052]

[0053] Ignoring the second-order terms, we have:

[0054]

[0055] Similarly, the observation operator H i In the forecast field Linearization at:

[0056]

[0057] Substituting the above formula into (1), we get the following incremental form of the objective function:

[0058]

[0059] Among them, H i , H i , The tangent operator of , the update vector is:

[0060]

[0061] The Newton optimization algorithm is used to solve the optimal analytical solution of variational fusion and calculate the gradient of the objective function, which can be used to obtain the multi-source data variational fusion observation operator, which is specifically characterized as follows:

[0062]

[0063] in, represents the adjoint mode of the tangent linear mode, is the adjoint of the observation operator, H i That is the observation operator.

[0064] After obtaining the above variational fusion observation operator, a variational fusion model is further constructed based on the above multi-source data and the variational fusion observation operator. According to the variational fusion model, a fusion operation can be performed on the data to generate an optimal mode field for deep fusion of power meteorological data and conventional observation data. At this time, a three-dimensional space grid is further constructed.

[0065] See also Figure 3 In an embodiment of the present invention, the step of determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field includes:

[0066] S31) determining the physical parameters to be analyzed based on the numerical prediction model analysis field;

[0067] S32) Determine the climate characteristics and disaster characteristics in the power operation area;

[0068] S33) obtaining an initial scale numerical prediction system;

[0069] S34) Processing the initial scale numerical forecasting system based on the physical parameters to be analyzed, the climate characteristics and the disaster characteristics to generate a three-dimensional grid setting scheme.

[0070] In a possible implementation, it is first necessary to determine the physical parameters for constructing a three-dimensional space grid. In an embodiment of the present invention, determining the physical parameters to be analyzed includes: performing physical parameter matching on the numerical forecast model analysis field to generate initial parameters; performing sensitivity analysis on the initial parameters to generate the most sensitive parameter combination; and optimizing the most sensitive parameter combination based on preset optimization features to generate the physical parameters to be analyzed.

[0071] Specifically, firstly, the physical parameter scheme of the best model is matched to match the physical parameters of the numerical forecast model analysis field. The best model can be predetermined by technical personnel, and initial parameters are generated after matching. At this time, a sensitivity analysis is performed on the initial parameters to determine the most sensitive parameter combination in the selected physical scheme; finally, the most sensitive parameter combination is optimized according to the preset optimization characteristics. Specifically, the most sensitive parameter combination can be optimized according to the meteorological characteristics of my country or the actual characteristics of the power operation scene to generate the physical parameters to be analyzed.

[0072] On the other hand, the main conditions and basis for setting up the three-dimensional spatial grid in the power operation area are analyzed, mainly including the basic characteristics of the weather and climate in the power operation area, and the characteristic ratio of the horizontal scale to the vertical scale of the disaster weather system in the power operation area, so as to determine the climate characteristics and disaster characteristics in the power operation area. Finally, an initial scale numerical prediction system is obtained. For example, the initial scale numerical prediction system is a scale numerical prediction system commonly used by technical personnel in this field. The existing setting scheme in the scale numerical prediction system is adjusted through the above-mentioned physical parameters to be analyzed, the climate characteristics and the disaster characteristics to generate the optimal three-dimensional grid setting scheme. Through the three-dimensional grid setting scheme, the spatial resolution of the model forecast results can be improved, and the dynamic downscaling effect of the numerical prediction model in the power operation area can be achieved.

[0073] Finally, the meteorological risk factors of power operations are extracted according to the three-dimensional grid setting scheme. Specifically, based on the output results of the dynamic downscaling numerical model, according to the specific type of power operation, operation scene, specific operation time and operation location, the meteorological risk factor values ​​that affect the safety of power operations are extracted: such as wind speed, wind direction, humidity, temperature, air pressure, precipitation, etc. Then, the corresponding risk identification results are generated according to the meteorological risk factors of power operations.

[0074] During the specific implementation process, based on the safety standards and safety work regulations for power meteorological operations, threshold judgments are made on the values ​​of meteorological risk factors, and risk identification and warnings are issued for meteorological factors that exceed the threshold range, thereby effectively identifying the meteorological risks of power operations.

[0075] In an embodiment of the present invention, multi-source data is used to identify meteorological risks in power operations, thereby improving the comprehensiveness of data and the accuracy of subsequent risk identification. Furthermore, the multi-source data is fused and analyzed to generate the best three-dimensional grid setting scheme to achieve the dynamic downscaling effect of the numerical forecast model in the power operation area, improve the precision of risk identification, and meet the actual needs of the enterprise.

[0076] The following describes an electric power operation risk identification device based on power downscaling technology provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0077] See also Figure 4Based on the same inventive concept, an embodiment of the present invention provides a device for identifying risks of electric power operations based on dynamic downscaling technology, the device comprising: a data acquisition unit for acquiring multi-source data; a fusion unit for fusing the multi-source data to generate a numerical forecast model analysis field; a grid setting unit for determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field; an extraction unit for extracting meteorological risk elements of electric power operations based on the three-dimensional grid setting scheme; and an identification unit for generating corresponding risk identification results based on the meteorological risk elements of electric power operations.

[0078] In an embodiment of the present invention, the fusion unit includes: an analysis module, which is used to perform observation error analysis on the multi-source data based on a preset covariance calculation rule to generate observation error covariance characteristics; a field generation module, which is used to generate an objective function based on the observation error covariance characteristics, and minimize the objective function to generate an optimal analysis field; an operator analysis module, which is used to perform operator analysis on the optimal analysis field based on an analysis increment to generate a corresponding variational fusion observation operator; a model construction module, which is used to construct a variational fusion model based on the multi-source data and the variational fusion observation operator; a fusion module, which is used to perform data fusion operations based on the variational fusion model to generate a numerical forecasting model analysis field.

[0079] In an embodiment of the present invention, the analysis module is specifically used to: determine the balance information of different variables in the multi-source data; calculate the standard deviation of different variables in the multi-source data; determine the self-adjoint smoothing factors of different variables in the multi-source data in different geographical directions; process the balance information, the standard deviation and the self-adjoint smoothing factor based on the control variable conversion algorithm to generate observation error covariance characteristics for the multi-source data.

[0080] In an embodiment of the present invention, the grid setting unit includes: a parameter determination module, which is used to determine the physical parameters to be analyzed based on the numerical prediction model analysis field; a feature determination module, which is used to determine the climate characteristics and disaster characteristics in the power operation area; a system acquisition module, which is used to acquire an initial-scale numerical prediction system; and a scheme determination module, which is used to process the initial-scale numerical prediction system based on the physical parameters to be analyzed, the climate characteristics and the disaster characteristics to generate a three-dimensional grid setting scheme.

[0081] In an embodiment of the present invention, the parameter determination module is specifically used to: perform physical parameter matching on the numerical forecast model analysis field to generate initial parameters; perform sensitivity analysis on the initial parameters to generate the most sensitive parameter combination; optimize the most sensitive parameter combination based on preset optimization features to generate physical parameters to be analyzed.

[0082] The optional implementation modes of the embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation modes. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical scheme of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.

[0083] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0084] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0085] In addition, various implementation modes of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed by the embodiments of the present invention.

Claims

1. A method for identifying risks of power operations based on dynamic downscaling technology, characterized in that: The method comprises: Acquire data from multiple sources; Performing fusion processing on the multi-source data to generate a numerical forecast model analysis field; Determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field; Extracting meteorological risk factors for power operations based on the three-dimensional grid setting scheme; Generate corresponding risk identification results based on the meteorological risk factors of the power operation; The determining of the three-dimensional grid setting scheme based on the numerical forecast model analysis field comprises: Determining the physical parameters to be analyzed based on the numerical prediction model analysis field; Determine the climate characteristics and disaster characteristics in the power operation area; Obtaining the initial scale numerical forecast system; Processing the initial scale numerical prediction system based on the physical parameters to be analyzed, the climate characteristics, and the disaster characteristics to generate a three-dimensional grid setting scheme; The step of determining the physical parameter to be analyzed comprises: Performing physical parameter matching on the numerical forecast model analysis field to generate initial parameters; Performing sensitivity analysis on the initial parameters to generate the most sensitive parameter combination; The most sensitive parameter combination is optimized based on the meteorological characteristics of the power operation area to generate physical parameters to be analyzed.

2. The method according to claim 1, characterized in that The fusing process of the multi-source data to generate a numerical forecast model analysis field includes: Performing observation error analysis on the multi-source data based on a preset covariance calculation rule to generate observation error covariance features; Generate an objective function based on the observation error covariance characteristics, perform minimization processing on the objective function, and generate an optimal analysis field; Performing operator analysis on the optimal analysis field based on the analysis increment to generate a corresponding variational fusion observation operator; Constructing a variational fusion model based on the multi-source data and the variational fusion observation operator; A data fusion operation is performed based on the variational fusion model to generate a numerical forecast pattern analysis field.

3. The method according to claim 2, characterized in that The performing observation error analysis on the multi-source data to generate observation error covariance features includes: Determining balance information of different variables in the multi-source data; Calculate the standard deviation of different variables in the multi-source data; Determining self-adjoint smoothing factors of different variables in the multi-source data in different geographic directions; The balance information, the standard deviation and the self-adjoint smoothing factor are processed based on a control variable conversion algorithm to generate observation error covariance characteristics for the multi-source data.

4. A power operation risk identification device based on dynamic downscaling technology, characterized in that: The device comprises: A data acquisition unit, used for acquiring multi-source data; A fusion unit, used for fusing the multi-source data to generate a numerical forecast model analysis field; A grid setting unit, used for determining a three-dimensional grid setting scheme based on the numerical forecast model analysis field; An extraction unit, used for extracting meteorological risk factors of power operations based on the three-dimensional grid setting scheme; An identification unit, used to generate corresponding risk identification results based on the meteorological risk factors of the power operation; The grid setting unit comprises: A parameter determination module, used for determining the physical parameters to be analyzed based on the numerical forecast model analysis field; A feature determination module, used to determine the climate characteristics and disaster characteristics in the power operation area; System acquisition module, used to obtain the initial scale numerical prediction system; A scheme determination module, used for processing the initial scale numerical prediction system based on the physical parameters to be analyzed, the climate characteristics and the disaster characteristics, and generating a three-dimensional grid setting scheme; The parameter determination module is specifically used for: Performing physical parameter matching on the numerical forecast model analysis field to generate initial parameters; Performing sensitivity analysis on the initial parameters to generate the most sensitive parameter combination; The most sensitive parameter combination is optimized based on the meteorological characteristics of the power operation area to generate physical parameters to be analyzed.

5. The device according to claim 4, characterized in that The fusion unit comprises: An analysis module, used to perform observation error analysis on the multi-source data based on a preset covariance calculation rule to generate observation error covariance features; A field generation module, used to generate an objective function based on the observation error covariance characteristics, perform minimization processing on the objective function, and generate an optimal analysis field; An operator analysis module, used for performing operator analysis on the optimal analysis field based on the analysis increment to generate a corresponding variational fusion observation operator; A model building module, used to build a variational fusion model based on the multi-source data and the variational fusion observation operator; The fusion module is used to perform data fusion operations based on the variational fusion model to generate a numerical forecast mode analysis field.

6. The device according to claim 5, characterized in that The analysis module is specifically used for: Determining balance information of different variables in the multi-source data; Calculate the standard deviation of different variables in the multi-source data; Determining self-adjoint smoothing factors of different variables in the multi-source data in different geographic directions; The balance information, the standard deviation and the self-adjoint smoothing factor are processed based on a control variable conversion algorithm to generate observation error covariance characteristics for the multi-source data.

Images